Non-Lethal Protection of Farmlands Against Wild Animals and Crop Estimation

Year : 2025 | Volume : 15 | Issue : 01 | Page : 18 24
    By

    Anvith Shankar B.,

  • Dheeraj Kumar Swamy B.,

  • Guru,

  • Abhiram D.,

  1. Student, Department of Electronics & Communication Engineering, Dayananda Sagar College of Engineering, Bengaluru, Karnataka, India
  2. Student, Department of Electronics & Communication Engineering, Dayananda Sagar College of Engineering, Bengaluru, Karnataka, India
  3. Student, Department of Electronics & Communication Engineering, Dayananda Sagar College of Engineering, Bengaluru, Karnataka, India
  4. Student, Department of Electronics & Communication Engineering, Dayananda Sagar College of Engineering, Bengaluru, Karnataka, India

Abstract

This paper is an integrated smart system that aims to enhance productivity related to agriculture along with agricultural safety through modern technology. Crop estimation system uses IoT sensors and machine learning algorithms for the analysis of real-time environmental data in terms of soil moisture, temperature, pH levels, and humidity. This data will further be used to provide the optimal crop for cultivation and appropriate fertilizer requirements for prediction of requirements. This will ensure that farmers can make data-informed decisions that will help maximize yield while using minimal resources. In addition to crop estimation, this paper addresses the problem of wild animals threatening farmland through deploying a non-lethal animal detection and deterrence system. The system uses an object detection algorithm named YOLOv5 to detect approaching animals, and the system identifies the species approaching then buzzes a buzzer, sprinkles water or turns on high-intensity lights and non-lethal electric shocks. The system is effective at keeping wild animals without harming them as it provides the best solutions to secure farmland with ecological balance and is humane. An integrated system results in higher farm security, maximum crop productivity, and sustainable agricultural practices. The invasion of farmlands by wild animals is a serious risk to agricultural output, resulting in monetary losses and disputes between people and wildlife. Sustainable ways to safeguard crops while maintaining ecological balance are provided by non-lethal techniques. This article discusses methods for precise crop prediction as well as cutting-edge non-lethal ways to protect farmlands from wild animals. These solutions combine technology like artificial intelligence (AI), sensor networks, and remote sensing to reduce conflict between humans and wildlife, increase agricultural productivity, and foster coexistence. The conversation focusses on realistic implementation techniques and how they could transform contemporary agriculture.

Keywords: Raspberry-pi, Sensors, Machine Learning, Object Detection, Crop Estimation, remote sensing

[This article belongs to Journal of VLSI Design Tools and Technology ]

How to cite this article:
Anvith Shankar B., Dheeraj Kumar Swamy B., Guru, Abhiram D.. Non-Lethal Protection of Farmlands Against Wild Animals and Crop Estimation. Journal of VLSI Design Tools and Technology. 2025; 15(01):18-24.
How to cite this URL:
Anvith Shankar B., Dheeraj Kumar Swamy B., Guru, Abhiram D.. Non-Lethal Protection of Farmlands Against Wild Animals and Crop Estimation. Journal of VLSI Design Tools and Technology. 2025; 15(01):18-24. Available from: https://journals.stmjournals.com/jovdtt/article=2025/view=195642


References

  1. Bouni, M., Hssina, B., Douzi, K., & Douzi, S. (2024). Integrated Iot Approaches for Crop Recommendation and Yield-Prediction Using Machine-Learning. IoT, 5(4), 634-649. https://doi.org/10.3390/iot5040028
  2. Zhang, M., Gao, F., Yang, W., & Zhang, H. (2023). Wildlife Object Detection Method Applying Segmentation Gradient Flow and Feature Dimensionality Reduction. Electronics, 12(2), 377. https://doi.org/10.3390/electronics12020377
  3. Benos, L., Tagarakis, A. C., Dolias, G., Berruto, R., Kateris, D., & Bochtis, D. (2021). Machine Learning in Agriculture: A Comprehensive Updated Review. Sensors, 21(11), 3758. https://doi.org/10.3390/s21113758
  4. Ma, Z., Dong, Y., Xia, Y., Xu, D., Xu, F., & Chen, F. (2024). Wildlife Real-Time Detection in Complex Forest Scenes Based on YOLOv5s Deep Learning Network. Remote Sensing, 16(8), 1350. https://doi.org/10.3390/rs16081350
  5. Kulyal and P. Saxena, “Machine Learning approaches for Crop Yield Prediction: A Review,” 2022 7th International Conference on Computing, Communication and Security (ICCCS), Seoul, Korea, Republic of, 2022, pp. 1-7, doi: 10.1109/ICCCS55188.2022.10079240.
  6. Krishna, P. A., Padhy, N., & Patnaik, A. (2024). Applying Machine Learning for Sustainable Farm Management: Integrating Crop Recommendations and Disease Identification. Engineering Proceedings, 67(1), 7073. https://doi.org/10.3390/engproc2024067073
  7. Yang, W., Liu, T., Jiang, P., Qi, A., Deng, L., Liu, Z., & He, Y. (2023). A Forest Wildlife Detection Algorithm Based on Improved YOLOv5s. Animals, 13(19), 3134. https://doi.org/10.3390/ani13193134
  8. Soussi, A., Zero, E., Sacile, R., Trinchero, D., & Fossa, M. (2024). Smart Sensors and Smart Data for Precision Agriculture: A Review. Sensors, 24(8), 2647. https://doi.org/10.3390/s24082647
  9. Davrazos, T. Panagiotakopoulos, S. Kotsiantis and A. Kameas, “IoT-Enabled Crop Recommendation in Smart Agriculture Using Machine Learning,” in 2023 14th International Conference on Information, Intelligence, Systems & Applications (IISA), Volos, Greece, 2023, pp. 1-4, doi: 10.1109/IISA59645.2023.10345924.
  10. Mahesh V Korde, Shivam R Varma, Pritesh N. Bhalerao, Tanvir T Shaikh, Atharv A Sonawane, “Crop Recommendation using Machine Learning & IoT,” International Research Journal of Modernization in Engineering Technology and Science, Apr. 2024; 6(04): 8059- 8067.
Regular Issue Subscription Review Article
Volume 15
Issue 01
Received 16/01/2025
Accepted 20/01/2025
Published 28/01/2025
Publication Time 12 Days
140


My IP

PlumX Metrics